INDEX

Explanations

terms related to stress and its health impacts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 fatally

-0.17

 leth

-0.14

Ð¾Ð½Ð°

-0.14

éľĩ

-0.14

thic

-0.14

æĩ

-0.13

 blindness

-0.13

 steril

-0.13

 deter

-0.13

 Lazy

-0.13

POSITIVE LOGITS

 stress

0.61

 Stress

0.58

stress

0.53

 stressed

0.43

 stressful

0.40

 stresses

0.38

 stressing

0.32

 tension

0.31

 cortisol

0.30

 Anxiety

0.28

Activations Density 0.100%

terms related to stress and its health impacts

No Comments

No Known Activations